VishalMysore's picture
Add MLC q0f16 weights converted from cycloneboy/CscSQL-Merge-Qwen2.5-Coder-0.5B-Instruct (SLM-SQL paper)
4c47c3d verified
Raw History Blame Contribute Delete
69.1 kB
{
"metadata": {
"ParamSize": 170,
"ParamBytes": 988065536.0,
"BitsPerParam": 12.543530476116773
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 272269312,
"records": [
{
"name": "model.embed_tokens.weight",
"shape": [
151936,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 272269312,
"byteOffset": 0
}
],
"md5sum": "bd9ff167784cef072e2088cda2ba70be"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 29826560,
"records": [
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 0
},
{
"name": "model.layers.0.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 1792
},
{
"name": "model.layers.0.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8718080
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26150656
},
{
"name": "model.layers.0.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26152448
},
{
"name": "model.layers.0.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26154752
},
{
"name": "model.layers.0.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28219136
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29824768
}
],
"md5sum": "185783a6217922fec5b17ce080523e26"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.1.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.1.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.1.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.1.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.1.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "37c8d98ac6c07a770e474e573f037795"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.10.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.10.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.10.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.10.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.10.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "0859da7f1bf97942eb7dd01d72a16c77"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.11.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.11.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.11.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.11.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.11.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "2a938dc17b32931729800fcbfe84ad38"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.12.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.12.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.12.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.12.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.12.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "7bab1ba4c210e780cbfcacd5da2052db"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.13.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.13.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.13.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.13.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.13.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "4896ef0eaa404a6e97d00f22acd8e16f"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.14.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.14.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.14.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.14.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.14.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "df95206bba3d9dccb3d49d16daf56cab"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.15.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.15.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.15.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.15.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.15.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "506cfca2a5590e1a6ea771cd8f2576ae"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.16.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.16.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.16.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.16.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.16.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.17.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "03fe95012155acc21c37c1a927e8b48c"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.17.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.17.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.17.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.17.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.17.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.18.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "e5fc9f42368e713e7eb161c247d7db9f"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.18.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.18.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.18.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.18.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.18.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.18.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.19.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "f76926125759e3c8dc2c291a1daaa2d7"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.19.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.19.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.19.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.19.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.19.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.19.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "e840c7e6e9cfc91ca7ff92a5cd9a350e"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.2.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.2.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.2.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.2.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.2.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.20.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "5c5ead5da0476b5eccae8a3f258ddd64"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.20.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.20.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.20.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.20.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.20.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.20.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.21.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "8a195767dde6b8d252665b095b447ada"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.21.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.21.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.21.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.21.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.21.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.21.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.22.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "e7ed168fb0a4c60741ea6313b7e6245b"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.22.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.22.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.22.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.22.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.22.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.22.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.23.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "24e50e7fe5384e724cbaf8e5df789b1f"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.23.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.23.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.23.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.23.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.23.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.23.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "c65334df467d57ee8e509370d556dac1"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.3.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.3.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.3.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.3.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.3.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "d45797a3150e256786b29b4c04e6f241"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.4.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.4.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.4.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.4.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.4.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "9ebde40ee3011768f0025ca49115f14b"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.5.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.5.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.5.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.5.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.5.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "911ecdc98d4b0297fe7f7b5a73d9704f"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.6.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.6.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.6.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.6.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.6.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "61369c5318f2df300e3bba47c2648b93"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.7.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.7.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.7.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.7.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.7.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "2418a1635cbd8f38b6074dfbd6595e5c"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.8.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.8.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.8.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.8.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.8.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "8a264af06ed4dbb5a7c98bb7fafb1b56"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.9.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.9.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.9.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.9.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.9.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.norm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "8d1f6df8e80c0be941fb62e0bf2f31b8"
}
]
}